2-3B Parameter LLMs — Page 38

purpur2

Psychologist-3b

Firefly-V2

Qwen3-1.7B-Flux-Prompt

HomePhi4_4B_FP16

machbase-llama3b

Phi-2-2.7B-Instruct-Medical-Conversational-v2

gemma-2b_ultrafeedback_chosen

Qwen3-1.7B_hh_helpful

meta-llama_Llama-3.2-3B-Instruct-GRPO-vanilla_G_4

ppo_adam_qwen3_1.7b

L3.2-JametMini-3B-MK.III

finemath-ablation-owm

Llama3.2-3B-Instruct-KAI

gemma-2-2b-it-fft-3epoch-simpo-adj

llama-3.2-3b-distilled-sleeper

ElioChat-1.7B-JP-v2-merged

Josiefied-Hermes-3-Llama-3.2-3B-v1

Llama-3.2-3B-Instruct_old_sft_alpaca_001

Llama-3.2-3B-Instruct_new_alpaca_005

qwen-2.5-3b-r1-countdown

vt-qwen-3b-GRPO-merged-16bit

Llama-3.2-3B-Instruct_new_alpaca_009

qwen3-1.7b-grpo-sft-base

ORANSight_Gemma_2_2B_Instruct

Qwen3-1.7B-Tiny-Hanabi-XML-SFT-5

Firefly-V2.5

sqlfuse_probgate_tsql_reasoning_prompt_only_answerable_delimeters_eos_8146

Alfworld-qwen2.5-3b-it-obs-2

guinius-giro-003

qwen3-1.7b-bilingual-amr-sft-v3

gemma-2-2b-Distillation-gemma-2-27b-it

Qwen2.5-Luau-Coder-3B

mash-authormist-essay

Qwen3-1.7B-MATH-RLVR-250-RE

lsda-3b-turkish-dev

Qwen3-1.7B-SFT-s1K-lr0_0001

arbor-treesearch-3b

llama_3.2_3b-owl_numbers_full_ep4

day1-train-model

llama_3.2_3b-owl_numbers_full_ep7

llama_3.2_3b-owl_numbers_full_ep10